Triple
T32669272
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AEVB |
E835244
|
entity |
| Predicate | typicalPrior |
P12230
|
FINISHED |
| Object | multivariate Gaussian prior |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: multivariate Gaussian prior | Statement: [AEVB, typicalPrior, multivariate Gaussian prior]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalPrior Context triple: [AEVB, typicalPrior, multivariate Gaussian prior]
-
A.
priorPost
Indicates that one post occurs earlier in sequence or time relative to another post.
-
B.
typicalPrecedent
Indicates that one situation, case, or event serves as a standard or commonly followed example for how similar later situations are handled.
-
C.
usesPrior
Indicates that an entity makes use of or relies on a previously existing or earlier version, instance, or state of something in performing an action or establishing a relationship.
-
D.
typicalIn
chosen
Indicates that something commonly occurs, appears, or is found within a given context, category, or environment.
-
E.
grandPrior
Indicates that one entity is the grandparent (parent of a parent) of another entity in a hierarchical or genealogical structure.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f349303ccc8190a70d0f6e8a21d3fb |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a037cad051c8190b28b354b89208574 |
completed | May 12, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_6a0379f0cbe481909b4b8fc6cbe297f0 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:08 a.m.